This HTML5 document contains 38 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
n17http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n12http://purl.org/net/nknouf/ns/bibtex#
n3http://localhost/temp/predkladatel/
n9http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n11http://linked.opendata.cz/ontology/domain/vavai/
n20https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n4http://linked.opendata.cz/ontology/domain/vavai/riv/
n7http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F61988987%3A17310%2F10%3AA1100YDH%21RIV11-MSM-17310___/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n6http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n14http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n13http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n19http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n15http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n16http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F61988987%3A17310%2F10%3AA1100YDH%21RIV11-MSM-17310___
rdf:type
skos:Concept n11:Vysledek
dcterms:description
The majority of this paper relies on some forms of automatic decomposition tasks into modules. Both described methods execute automatic neural network modularization. Modules in neural networks emerge; we do not build them straightforward by penalizing interference between modules. The concept of emergence takes an important role in the study of the design of neural networks. In the paper, we study an emergence of modular connectionist architecture of neural networks, in which networks composing the architecture compete to learn the training patterns directly from the interaction of reproduction with the task environment. Network architectures emerge from an initial set of randomly connected networks. In this way can be eliminated connections so as to dedicate different portions of the system to learn different tasks. Mentioned methods were demonstrated for experimental task solving. The majority of this paper relies on some forms of automatic decomposition tasks into modules. Both described methods execute automatic neural network modularization. Modules in neural networks emerge; we do not build them straightforward by penalizing interference between modules. The concept of emergence takes an important role in the study of the design of neural networks. In the paper, we study an emergence of modular connectionist architecture of neural networks, in which networks composing the architecture compete to learn the training patterns directly from the interaction of reproduction with the task environment. Network architectures emerge from an initial set of randomly connected networks. In this way can be eliminated connections so as to dedicate different portions of the system to learn different tasks. Mentioned methods were demonstrated for experimental task solving.
dcterms:title
Automatic Modularization of Artificial Neural Networks Automatic Modularization of Artificial Neural Networks
skos:prefLabel
Automatic Modularization of Artificial Neural Networks Automatic Modularization of Artificial Neural Networks
skos:notation
RIV/61988987:17310/10:A1100YDH!RIV11-MSM-17310___
n4:aktivita
n8:S
n4:aktivity
S
n4:dodaniDat
n16:2011
n4:domaciTvurceVysledku
n9:3494667
n4:druhVysledku
n19:D
n4:duvernostUdaju
n14:S
n4:entitaPredkladatele
n7:predkladatel
n4:idSjednocenehoVysledku
248190
n4:idVysledku
RIV/61988987:17310/10:A1100YDH
n4:jazykVysledku
n13:eng
n4:klicovaSlova
artificial neural networks; modular architecture; comparative study
n4:klicoveSlovo
n6:comparative%20study n6:artificial%20neural%20networks n6:modular%20architecture
n4:kontrolniKodProRIV
[81DEB0D6576B]
n4:mistoKonaniAkce
Funchal
n4:mistoVydani
Portugal
n4:nazevZdroje
Proceedings of the 6th International Workshop on Artificial Neural Networks and Intelligent Information Processing, ANNIIP
n4:obor
n15:IN
n4:pocetDomacichTvurcuVysledku
1
n4:pocetTvurcuVysledku
1
n4:rokUplatneniVysledku
n16:2010
n4:tvurceVysledku
Volná, Eva
n4:typAkce
n17:WRD
n4:zahajeniAkce
2010-06-17+02:00
s:numberOfPages
10
n12:hasPublisher
In conjunction with ICINCO 2010.
n20:isbn
978-989-8425-03-4
n3:organizacniJednotka
17310